Skip to main content
Connic

AWS SQS

By Connic

Connic polls your SQS queue, runs your agents on each message, and deletes it only when every run completes. Failures redeliver via the visibility timeout into your DLQ policy, and you don't run the workers.

InboundOutbound

Overview

Give the connector a queue URL, a region, and scoped IAM credentials, and Connic long polls the queue for you. Each message body is parsed as JSON and dispatched to your linked agents with the queue metadata attached under _sqs: message ID, receipt handle, queue URL, receive count, and sent timestamp. The message is deleted only when every linked agent's run completes; if a run fails, the message stays on the queue and reappears after the visibility timeout.

That is the entire worker fleet. Polling cadence, batch size, and visibility timeout are connector settings rather than code, and retry behavior falls out of SQS semantics you already know: failed messages retry, and repeat failures land in whatever dead-letter queue you configure in AWS.

How it works

1

Create the queue and an IAM user

Use a standard or FIFO queue and grant the IAM user sqs:ReceiveMessage, sqs:DeleteMessage, sqs:ChangeMessageVisibility, and sqs:GetQueueAttributes on it. Outbound connectors need sqs:SendMessage and sqs:GetQueueAttributes on the target queue instead.

2

Create the connector

Add an AWS SQS connector from your agent's Connector Flow in Inbound mode, then enter the queue URL, region, and AWS credentials. Tune Max Messages (1 to 10 per poll), Wait Time (long polling up to 20 seconds), and Visibility Timeout (300 seconds by default).

3

Link agents, optionally publish results

Connic starts polling and dispatches each message to all linked agents. Add an outbound connector pointing at another queue and completed run results are sent there for downstream processing.

What you can build

Patterns teams ship in production. No queues, workers, or schedulers to run.

Trigger

Order lands in queue

sqs://orders-queue
Agent Action

Agent pulls customer history, confirms stock, picks a carrier, and emits a fulfillment job to the next queue — keeping the checkout API on its 200ms budget.

Message lifecycle and retries

Messages are fetched with long polling (20 seconds by default) to keep empty responses and API calls down. A message is deleted from the queue only after every linked agent's run completes; a failed run leaves it in place, so it becomes visible again after the visibility timeout and is retried. While runs are in flight, Connic extends the message's visibility automatically, so a long run does not cause premature redelivery. For messages that fail repeatedly, configure a dead-letter queue on the AWS side and they end up there for inspection and replay.

Each message becomes a normal agent run, with full traces, token and cost tracking, and the same guardrails and approval rules as any other trigger. When a message keeps bouncing, the run history shows you exactly why.

Result payloads and FIFO queues

Outbound connectors publish a JSON result for each completed run: run_id, agent_name, status, output, error, timestamps, and token_usage. For FIFO queues, set a Message Group ID to keep ordering within a group; the deduplication ID is set to the run ID, so a result is never enqueued twice. See the payload formats and IAM policies in the SQS docs.

Information

Publisher
By Connic
Category
Connectors
Modes
Inbound, Outbound
Documentation
AWS SQS docs

Frequently Asked Questions

How do I process SQS messages with an AI agent?

Create an AWS SQS connector in Inbound mode with your queue URL, region, and IAM credentials, then link it to an agent. Connic long polls the queue, runs the agent on each message, and deletes messages after successful processing. There is no consumer service or worker fleet to run. For the wider picture, explore common connector patterns.

What happens when an agent run fails?

Two safety nets stack. The runner first retries the run automatically with exponential backoff (configurable per agent). If the run still fails, the message is not deleted: it returns to the queue after the visibility timeout and is retried, and repeatedly failing messages flow to the dead-letter queue you configure in AWS for inspection and replay.

Does the SQS connector support FIFO queues?

Yes, both standard and FIFO queues work. For outbound FIFO queues, configure a Message Group ID so results with the same group are delivered in order; the message deduplication ID is set to the run ID.
Need AWS SQS in a production agent flow?

Bring the event source, payload shape, result destination, and any private-network or approval requirements. We will map AWS SQS to the right Connic connector mode, deployment path, and observability setup.

Talk to Sales